Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add JustineDevs/premortem --skill cloud-securitygit clone --depth 1 https://github.com/JustineDevs/premortemWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/justinedevs/premortem/cloud-security)<a href="https://agentmods.dev/skills/justinedevs/premortem/cloud-security"><img src="https://agentmods.dev/badge/skills/justinedevs/premortem/cloud-security/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/justinedevs/premortem/cloud-security"><img src="https://agentmods.dev/badge/skills/justinedevs/premortem/cloud-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.02114 |
| Opus 5 | $0.00043 | $0.01057 |
| Sonnet 5 | $0.00017 | $0.00423 |
| Haiku 4.5 | $0.00009 | $0.00211 |
Grade A, and why
cloud-security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Security Assessment
Thin router for security assessment of AWS, GCP, and Azure environments. The body of knowledge lives in per-cloud references/, per-domain methodology/, and per-scope workflows/. Load only what the current task needs.
When to Use
- Multi-cloud or single-cloud security audit (read-only CSPM-style).
- IAM privilege-escalation path discovery.
- Storage (S3 / GCS / Azure Blob) exposure review.
- Network posture and metadata-service checks.
- Secrets-store audit (Secrets Manager / Secret Manager / Key Vault).
- CIS / SOC2 / PCI-DSS benchmark assessment against a live account.
- Cross-cloud identity federation / trust-graph review.
Trigger Phrases
audit AWS security, scan Azure for misconfigurations, check GCP security, test cloud IAM, find S3 bucket issues, cloud penetration test, CIS benchmark audit, cloud privilege escalation, multi-cloud assessment.
When NOT to Use This Skill
| If the task is… | Use instead |
|---|---|
| Scanning Terraform / CloudFormation / ARM / Bicep / Pulumi files pre-deploy | iac-security |
| Container image CVEs or scanning running workloads on EKS / GKE / AKS | container-security |
| Testing an application hosted in the cloud (OWASP, BOLA, XSS, SQLi) | api-security or dast-automation |
| Source-code SAST of cloud-deployed apps | sast-orchestration |
| LLM-specific attacks against a cloud-hosted model | llm-security |
This skill assumes you have credentials against a live cloud account. If you only have source artifacts, route to the sibling skills above.
Decision Tree
Target scope?
├─ Single cloud (AWS only) → workflows/aws_full_assessment.md
├─ Single cloud (GCP only) → workflows/gcp_full_assessment.md
├─ Single cloud (Azure only) → workflows/azure_full_assessment.md
└─ 2+ clouds / federated → workflows/cross_cloud_comparison.md (fan out per-cloud)
Within a cloud, narrow by domain:
├─ IAM / identity / privesc → methodology/iam_privilege_escalation.md
├─ Storage exposure (S3/GCS/Blob) → methodology/storage_misconfig.md
├─ Networking / firewall / IMDS → methodology/network_security.md
├─ Secrets / KMS / Key Vault → methodology/secrets_management.md
└─ CIS/compliance full sweep → the workflow for that cloud (runs scanners)
Need specific commands or tool invocations?
├─ AWS → references/aws.md
├─ GCP → references/gcp.md
├─ Azure → references/azure.md
├─ Tooling → references/cloud_tools.md
└─ SQL → references/steampipe_queries.sql
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- methodology/iam_privilege_escalation.md 10 KB
- methodology/network_security.md 6.2 KB
- methodology/secrets_management.md 6.9 KB
- methodology/storage_misconfig.md 5.7 KB
- references/aws.md 7.2 KB
- references/azure.md 7.9 KB
- references/bounty_patterns_2024_2026.md 13 KB
- references/cloud_tools.md 5.5 KB
- references/gcp.md 6.7 KB
- references/steampipe_queries.sql 8.6 KB
- schemas/finding.json 2.6 KB
- workflows/aws_full_assessment.md 3.8 KB
- workflows/azure_full_assessment.md 4.8 KB
- workflows/cross_cloud_comparison.md 5.3 KB
- workflows/gcp_full_assessment.md 4.0 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 157 lines · 85 tokens per session scan A 042b9d543f3d
cloud-security is a skill published in the GitHub repository JustineDevs/premortem (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 2,114 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
awesome-azd-template-submit
Submit an azd template to the awesome-azd gallery. Use when asked to submit, add, or contribute a template to awesome-azd. Requires only a GitHub repository URL — all metadata (title, description, languages, frameworks, Azure services, IaC) is auto-detected by the submission pipeline.
azure-cli
Use the Azure CLI to manage subscriptions, resource groups, AKS, App Service, Key Vault, and role assignments.
azure-cli
A command-line tool for managing Microsoft Azure, Microsoft's cloud platform, from a terminal. It covers account sign-in, subscriptions, resource groups, virtual machines, and other cloud resources.
aws-cli
CLI-first AWS orchestration skill for Lambda, ECS/Fargate, and S3 workflows rooted in .☁️ runbooks.
azure-eventhub-dotnet
Azure Event Hubs SDK for .NET. Use for high-throughput event streaming: sending events (EventHubProducerClient, EventHubBufferedProducerClient), receiving events (EventProcessorClient with checkpointing), partition management, and real-time data ingestion. Triggers: "Event Hubs", "event streaming"…
azure-resource-manager-durabletask-dotnet
Azure Resource Manager SDK for Durable Task Scheduler in .NET. Use for MANAGEMENT PLANE operations: creating/managing Durable Task Schedulers, Task Hubs, and retention policies via Azure Resource Manager. Triggers: "Durable Task Scheduler", "create scheduler", "task hub", "DurableTaskSchedulerResource", "provision…